<?xml version="1.0" standalone="yes"?>
<Paper uid="P01-1037">
  <Title>The Role of Lexico-Semantic Feedback in Open-Domain Textual Question-Answering</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
Open-domain textual Question-Answering
</SectionTitle>
    <Paragraph position="0"> (Q&amp;A), as defined by the TREC competitions1, is the task of identifying in large collections of documents a text snippet where the answer to a natural language question lies. The answer is constrained to be found either in a short (50 bytes) or a long (250 bytes) text span. Frequently, keywords extracted from the natural language question are either within the text span or in its immediate vicinity, forming a text paragraph. Since such paragraphs must be identified throughout voluminous collections, automatic and autonomous Q&amp;A systems incorporate an index of the collection as well as a paragraph retrieval mechanism.</Paragraph>
    <Paragraph position="1"> Recent results from the TREC evaluations ((Kwok et al., 2000) (Radev et al., 2000) (Allen  workshops organized by the National Institute of Standards and Technology (NIST), designed to advance the state-of-the-art in information retrieval (IR) et al., 2000)) show that Information Retrieval (IR) techniques alone are not sufficient for finding answers with high precision. In fact, more and more systems adopt architectures in which the semantics of the questions are captured prior to paragraph retrieval (e.g. (Gaizauskas and Humphreys, 2000) (Harabagiu et al., 2000)) and used later in extracting the answer (cf. (Abney et al., 2000)).</Paragraph>
    <Paragraph position="2"> When processing a natural language question two goals must be achieved. First we need to know what is the expected answer type; in other words, we need to know what we are looking for. Second, we need to know where to look for the answer, e.g. we must identify the question keywords to be used in the paragraph retrieval.</Paragraph>
    <Paragraph position="3"> The expected answer type is determined based on the question stem, e.g. who, where or how much and eventually one of the question concepts, when the stem is ambiguous (for example what), as described in (Harabagiu et al., 2000) (Radev et al., 2000) (Srihari and Li, 2000). However finding question keywords that retrieve all candidate answers cannot be achieved only by deriving some of the words used in the question. Frequently, question reformulations use different words, but imply the same answer. Moreover, many equivalent answers are phrased differently. In this paper we argue that the answer to complex natural language questions cannot be extracted with significant precision from large collections of texts unless several lexico-semantic feedback loops are allowed.</Paragraph>
    <Paragraph position="4"> In Section 2 we survey the related work whereas in Section 3 we describe the feedback loops that refine the search for correct answers.</Paragraph>
    <Paragraph position="5"> Section 4 presents the approach of devising key-word alternations whereas Section 5 details the recognition of question reformulations. Section 6 evaluates the results of the Q&amp;A system and Sec-</Paragraph>
  </Section>
class="xml-element"></Paper>